Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4592 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1778678 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1943. Min Act: -0.0000

Data Index: 828377 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2044. Min Act: -0.0000

Data Index: 143143 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2305. Min Act: -0.0000

Data Index: 33376 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.2046. Min Act: -0.0000

Data Index: 454701 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1408842 (The Pile)

Max Activating Token Index: 306

Text #6

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1747. Min Act: 0.0000

Data Index: 503554 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1173358 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1632. Min Act: -0.0000

Data Index: 923372 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1617. Min Act: -0.0000

Data Index: 936517 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1584. Min Act: 0.0000

Data Index: 1936454 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1553. Min Act: -0.0000

Data Index: 143563 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1329782 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1411. Min Act: 0.0000

Data Index: 1647865 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1531. Min Act: 0.0000

Data Index: 1503015 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1527. Min Act: -0.0000

Data Index: 16359 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1534. Min Act: 0.0000

Data Index: 715092 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1171960 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1629. Min Act: 0.0000

Data Index: 1416610 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.2305. Min Range: -0.2305

Max Act: 0.1540. Min Act: -0.0000

Data Index: 338021 (The Pile)

Max Activating Token Index: 639